[all-commits] [llvm/llvm-project] c76067: [AMDGPU] Update base addr of dyn alloca considerin...

[Aaditya via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c7606710f93cf0ab655a5bcbbf873954051ba109
      https://github.com/llvm/llvm-project/commit/c7606710f93cf0ab655a5bcbbf873954051ba109
  Author: Aaditya <115080342+easyonaadit at users.noreply.github.com>
  Date:   2024-12-20 (Fri, 20 Dec 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/GlobalISel/dynamic-alloca-uniform.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/non-entry-alloca.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-dyn-stackalloc.mir
    M llvm/test/CodeGen/AMDGPU/amdpal-callable.ll
    M llvm/test/CodeGen/AMDGPU/non-entry-alloca.ll

  Log Message:
  -----------
  [AMDGPU] Update base addr of dyn alloca considering GrowingUp stack (#119822)

Currently, compiler calculates the base address of
dynamic sized stack object (alloca) as follows:
1. `NewSP = Align(CurrSP + Size)`
_where_ `Size = # of elements * wave size * alloca type`
2. `BaseAddr = NewSP`
3. The alignment is computed as: `AlignedAddr = Addr & ~(Alignment - 1)`
4. Return the `BaseAddr`
This makes sense when stack is grows downwards.

AMDGPU stack grows upwards, the base address 
needs to be aligned first and SP bump by required size later:
1. `BaseAddr = Align(CurrSP)`
2. `NewSP = BaseAddr + Size`
3. `AlignedAddr = (Addr + (Alignment - 1)) & ~(Alignment - 1)`
4. and returns the `BaseAddr`.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications